© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31003
    Prev
    Next
    INDEX
    Explanations

    letter and symbol mappings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ירת
    0.47
     बिज़
    0.46
    ٢
    0.46
    পালের
    0.44
    ☒
    0.44
    Ꮝ
    0.43
    ठभे
    0.43
    ="<?=
    0.43
    ١
    0.43
    घाटन
    0.42
    POSITIVE LOGITS
    )
    0.45
    0.41
    ]
    0.41
     etc
    0.39
    。
    0.39
        
    0.37
    ↵↵
    0.36
    Base
    0.35
    exe
    0.35
     div
    0.34
    Activations Density 0.006%

    No Known Activations